Sergey Filimonov comments

Results 39 comments of


                                            Sergey Filimonov

add langchain document support

Great! `embedding` is used for semantic processing (combining chunks by similarity) - yes it's a vector from OpenAI (long term maybe agnostic). Tiktoken is our current method for calculating tokens...

Table Extraction Tool

I will look into this, it'd be helpful if they published more benchmarks of their work. I'm also concerned on the relatively small amount of data it was trained on....

Method to convert `ParsedDocument` object to LlamaIndex `Document` object

Can you point me to documentation that explains how Nodes and Documents are related in llama_index? From what I understand a Document is just a parent Node. This is the...

Clear

Ok thanks for clarifying - I learned something today about poetry. What is the correct way to bump to the latest version available (even if it's outside of your explicit...

Clear

Ok thanks that's helpful. Maybe it would be helpful to have a section in the docs explaining this? I imagine many users are coming from `pip freeze > requirements.txt` and...

Inquiry About Future Updates and Forking Possibility

Seconded

cohere_client = cohere.ClientV2 returned "Resource not found error"

For other people dealing with this it seems like there's two ways of deploying cohere on Azure that are quite different. ## 1. Serverless Endpoint This was the default for...

Adding support for Azure OpenAI

Thanks for the PR - this would be a pretty large breaking change. If we're going to do that, I think the best approach is to pass an embedding client...

add the code for the pdf table parser with pdf plumber

Thanks for the PR - I will take a look this week